Data Analytics Can Improve Drug Development

Increased use of technology and data comes at a time when the pharmaceutical industry is booming, with hundreds of new drugs created in the past 20 years.

Improved understanding of diseases, as well as widely-available patient and genetic data has led to significant advances in the healthcare industry, according to a new report from the QuintilesIMS Institute for Healthcare Informatics.

Drug development is now heading towards more personalized treatment approaches that are expected to drive outcomes, which can only be possible through the use of big data and analytics. However, these new advancements require the use of advanced technology and data management, as well as collaboration among stakeholders, according to the report.

The use of data has already been largely implemented in the oncology space. The increasing number of cancer drugs and the patients receiving those treatments all leave behind a trail of data that can be used to determine the value of the drug, in addition to drug spending trends, which has been a topic of interest as the industry starts to move towards value-based healthcare.

With reimbursements tied to drug efficacy, it is important that manufacturers use patient outcome data from clinical trials and the real world to ensure that patients are receiving the most optimal treatment. The clinical trial itself can also greatly benefit from the use of data, QuintilesIMS Institute said.

“Drug costs and spending are being scrutinized more intensely worldwide. At the same time, the challenges associated with developing new medicines remain extraordinarily high,” said Murray Aitken, senior vice president and executive director of the QuintilesIMS Institute. “This confluence of pressures will lead to a crisis in biomedical innovation unless the industry applies a more strategic approach—one that links actionable insights earlier in clinical development and commercialization.”

The report highlights 9 evidence-based approaches to using patient data and analytics more effectively:

1. Study Design

Clinical trials use primary and secondary endpoints to examine if the investigational product aligns with the intended indications. By using real-world insights and data, researchers can reach validation of endpoints quickly.

2. Better Study Criteria

Biomarker identification can be conducted relatively easily through gene expression profiling, genetic analysis, and genomic profiling in clinical studies, as well as in the real world, according to QuintilesIMS Institute.

3. Site of the Clinical Trial

The location of a clinical trial is extremely important, and has the potential to affect outcomes. New analytics can be applied to increase enrollment in the studies and decrease protocol changes.

4. Conducting Clinical Trials Effectively

Site monitoring accounts for 21% of the cost of the clinical trial, which makes it the highest cost factor, according to the report. Using risk-based monitoring is an effective way to identify risks before problems arise and create additional costs. Data about the sites, type of study, and indication of the drug allow big data tools to identify the potential risks.

5. Improving Care and Outcomes Analysis

Analyzing real-world treatment patterns, resource utilization, and patient outcomes data can provide useful insights to improve patient care. Other sources of data, such as electronic health records and claims databases alongside clinical research can provide even more insights.

6. Medication Nonadherence

Nonadherence to medications can result in poor patient outcomes, and unnecessary medical costs. With the shift towards value-based healthcare, this issue is concerning to stakeholders. Data analytics can be used to gain a better understanding of the causes of nonadherence, stratify patients based on risk analysis, implement low-cost interventions, and add adherence strategies to patient records, according to the report.

7. Provide the Right Medications to the Right People

Real-world data analytics allows for more understanding of a patient’s overall health, and can allow stakeholders to better identify which physicians may benefit from a new medication. Once identified, manufacturers can provide information about the medication to the providers.

8. Integrating Value into Decision Making

Value-based healthcare requires a multitude of new measures to determine what makes a medication “valuable.” Stakeholders may have to review medical records, claims data, mortality rate, consumer data, registries, and data from studies to discover the value, according to the report.

9. Using Post-Market Data Effectively

Some manufacturers face the difficulties of not having enough precise data, including those developing treatments for rare diseases. These manufacturers must use real-world data to measure patient populations and fix the gaps to improve the available data.

“Properly harnessed, data analytics can drive remarkable progress in allocating healthcare resources, developing and commercializing new medicines, as well as improving population outcomes,” Aitken concluded.